Title :
Seizure prediction in epilepsy: From circadian concepts via probabilistic forecasting to statistical evaluation
Author :
Schelter, Björn ; Feldwisch-Drentrup, Hinnerk ; Ihle, Matthias ; Schulze-Bonhage, Andreas ; Timmer, Jens
Author_Institution :
Fac. of Math. & Phys., Univ. of Freiburg, Freiburg, Germany
fDate :
Aug. 30 2011-Sept. 3 2011
Abstract :
Seizure prediction performance is hampered by high numbers of false predictions. Here we present an approach to reduce the number of false predictions based on circadian concepts. Based on eight representative patients we demonstrate that this approach increases the performance considerably. The fraction of patients for whom we found a significant seizure prediction performance was increased from 25% to 38% by accounting for circadian dependencies.
Keywords :
circadian rhythms; diseases; electroencephalography; forecasting theory; medical signal processing; prediction theory; statistical analysis; circadian concepts; circadian dependencies; epilepsy; probabilistic forecasting; seizure prediction; statistical evaluation; Electroencephalography; Epilepsy; Prediction algorithms; Prediction methods; Probabilistic logic; Sensitivity; Surgery; Adult; Algorithms; Child; Circadian Rhythm; Data Interpretation, Statistical; Diagnosis, Computer-Assisted; Electroencephalography; Female; Forecasting; Humans; Male; Middle Aged; Reproducibility of Results; Seizures; Sensitivity and Specificity;
Conference_Titel :
Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-4121-1
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2011.6090469
